cloudstack-llc/mlx-knife
1
0
Fork 0
mirror of https://github.com/cloudstack-llc/mlx-knife.git synced 2026-07-21 18:15:37 -04:00
Code Issues Packages Projects Releases Wiki Activity
22 Commits 4 Branches 53 Tags
archive/dev
Commit Graph

9 Commits

Author SHA1 Message Date
The BROKE Cluster Team ce46601d9d Release: 1.1.1-beta.3 - MXFP4 support and GPT-OSS reasoning 
• MXFP4 Quantization Support (MLX ≥0.29.0, MLX-LM ≥0.27.0)
• GPT-OSS Reasoning Models with --hide-reasoning flag
• Enhanced Show Command with improved quantization display
• Documentation updates (README.md, TESTING.md)

See CHANGELOG.md for complete technical details.
Partial Issue #32 (GPT-OSS only, other reasoning models remain open).
 2025-09-10 13:32:04 +02:00
Local Test 5045f9e1bd Release: 1.1.1‑b2 — Issue #31, stable server tests 
- Lenient MLX detection via README/tokenizer (Issue #31)
- CLI: `show` type, strict `list` (chat), `run` accepts private MLX
- Server tests: RAM‑aware gating with `mlxk show`, MoE parsing fix (8x7B), server‑manager process guard, thread‑based timeout
- Multi‑Python script hardened; no ANSI; log tail on errors
- Docs: CHANGELOG, TESTING, CLAUDE updated; 166/166 green (Py 3.9–3.13), 32 server tests green
 2025-09-07 02:24:08 +02:00
The BROKE Team cf169e28ad Release MLX Knife 1.1.0 - Stable Release 
Complete isolated test system with 150/150 tests passing.
  Production-ready after successful beta testing cycle.

  See CHANGELOG.md for comprehensive details including:
  - All critical issues from 1.1.0-beta3 resolved
  - Enhanced test infrastructure with real model validation
  - Multi-Python compatibility (3.9-3.13)
 2025-08-26 16:30:12 +02:00
The BROKE Team 7d0d6be66d Release MLX Knife 1.1.0-beta3 - Critical Cache Management Fixes 
Three major bug fixes for production readiness:

- Issue #21: Fix crash on fresh installations (empty cache directory)
- Issue #22: Suppress urllib3 LibreSSL warnings on macOS Python 3.9
- Issue #23: Fix double rm execution bug - models now deleted in single command

Test improvements:
- 140/140 tests passing (up from 137)
- Added real integration tests for lock cleanup
- Fixed unit tests broken by path corrections

All known cache management issues resolved for stable release.
 2025-08-26 01:46:40 +02:00
The BROKE Team 1aad374d08 Release MLX Knife 1.1.0-beta2 - Critical Bug Fixes & Test Stability 
Major fixes:
  - Issue #19: Server response truncation resolved - large context models work at full capacity
  - Issue #20: End-Token filtering in non-streaming mode - clean professional output
  - Test stability: Fixed flaky server tests, improved lifecycle management

  Technical changes:
  - Server: Dynamic token limits by default (--max-tokens None)
  - MLXRunner: Added _filter_end_tokens_from_response() for batch consistency
  - Tests: 132/132 passing + 48 comprehensive server tests
  - Documentation: Updated CHANGELOG.md, README.md, TESTING.md
 2025-08-22 23:16:50 +02:00
The BROKE Team 74239c4e43 Release MLX Knife 1.1.0-beta1 - Dynamic Token Limits & Enhanced Web Client 
Issues Resolved:
  • Issue #15: Token limits vs natural stop tokens race condition - FIXED
  • Issue #16: Interactive vs server token limit policies - FIXED

  Major Improvements:
  • Automatic optimal token limits - no configuration needed
  • Manual --max-tokens control still available when desired
  • Eliminates old hardcoded 500/2000 token restrictions
  • Performance gains: Up to 524x improvement for large context models
  • Enhanced web client with model capabilities display and better UX

  Additional Enhancements:
  • Enhanced /v1/models API with context_length field
  • Comprehensive test expansion: 114 → 131 tests (131/131 passing)
  • Python 3.9-3.13 compatibility verified

  Known Issues (Beta Status):
  • Server deadlock possible under extreme concurrent model loading stress
  • Workaround: Avoid simultaneous heavy model operations
 2025-08-21 17:36:44 +02:00
The BROKE Team 6117e571ca Release MLX Knife 1.0.4 - Issue #14 Chat Self-Conversation Fix & Web UI Overhaul 
Fix Issue #14: Interactive chat self-conversation bug resolved
  - Added context-sensitive chat stop tokens (\nHuman:, \nAssistant:, \nYou:, \nUser:)
  - Smart priority system: native model stop tokens first, chat tokens as fallback
  - Affects both `mlxk run` and `mlxk server` modes with backward compatibility

  Web UI complete transformation (simple_chat.html):
  - 🦫 Beaver branding replaces 🔪 knife emoji
  - Model and chat history persistence across browser sessions
  - Smart model switching with option to keep or clear chat history

  Testing infrastructure enhancements:
  - Automated server testing with RAM-aware model filtering
  - 15 new regression tests across 7+ MLX models validating Issue #14 fix
  - Comprehensive TESTING.md guide for server-based testing

  All 114 tests passing
 2025-08-19 20:43:44 +02:00
The BROKE Team cbd25c658d Release MLX Knife 1.0.2 - HF_HOME Cache Consistency & Corruption Fixes │ 
│                                                                                                      │
│   Major bug fixes addressing cache path inconsistencies and silent failures:                         │
│   - Fix Issue #11: HF_HOME environment variable handling - unified cache logic ensures consistent    │
│   /hub subdirectory usage                                                                            │
│   - Fix Issue #9: Silent failure on corrupted models with empty snapshots directories                │
│   - Enhanced download throttling with adaptive delays (512KB chunks, 2-3s for large files)           │
│   - Added migration warnings for legacy cache locations with clear user guidance                     │
│   - Improved corruption detection and deletion workflow consistency                                  │
│                                                                                                      │
│   Technical improvements:                                                                            │
│   - Unified cache architecture: CACHE_ROOT/hub for both default and HF_HOME scenarios                │
│   - Exception-safe memory management with enhanced baseline tracking                                 │
│   - Updated dependencies to latest tested versions (Python 3.9-3.13 support)                         │
│   - All 105 tests passing with real MLX model verification
 2025-08-18 14:02:30 +02:00
mzfive 6b04448d1c Initial commit: MLX Knife 1.0-rc1 2025-08-12 23:00:55 +02:00